Legal provision semantic annotation method and device based on LSTM network

• Main Authors: MO TONG, LIU YATING, LUO XUHUI, ZHANG YIXUAN, LI YUMENG
• Format: Patent
• Language: Chinese; English
• Published: 28.07.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention relates to a legal provision semantic annotation method and device based on an LSTM network. The method comprises the steps of obtaining a to-be-analyzed text; analyzing the to-be-analyzed text to obtain all words and part-of-speech tagging corresponding to the words of the to-be-analyzed text, converting the words and the part-of-speech tagging into D-dimensional word vectors, and inputting the D-dimensional word vectors into the full-connection neural network to obtain feature codes; comparing the part-of-speech tagging of the to-be-analyzed text with the part-of-speech taggingof the text in a preset database to obtain a most matched text, and obtaining a final vector representation; inputting the final vector representation into a fully connected neural network, and outputting a semantic role label of each word in the to-be-analyzed text. According to the invention, factors such as an applicant, a receiver, time and a place in the legal provision can be automaticallyanalyzed, related personne